W3C Standard Simplifies Creation of Speech-Enabled Web Applications

W3C published today a standard that will simplify the development of Web applications that speak and listen to users. The Pronunciation Lexicon Specification (PLS) 1.0 is the newest piece of W3C's Speech Interface Framework for creating Web applications driven by voice and speech. PLS can reduce the cost of developing these applications by allowing people to share and reuse pronunciation dictionaries. In addition, PLS can make it easier to localize applications by separating pronunciation concerns from other parts of the application. [click heading for more]

Fonix Releases iSpeak Embedded Speech App for iPhone

Officials at Fonix Speech, Inc. say their iSpeak 1.0 product now can be purchased for $15 at the App Store. Using the powerful iPhone is made easier with Fonix iSpeak, according to Steve Jones, the company’s senior sales executive. [click heading for more]

Eric – New Hollywood Star

IVO Software has presented Eric – the latest English-speaking male voice based on IVONA – text-to-speech technology regarded as one of the best in the world.  Eric comes from Hollywood and experts describe his way of speaking as “CNN style”.  Listening to Eric you get the impression that this is a person from the West Coast of the US talking to you. This is no accident as IVONA is speaking with the voice of an artist heard in Hollywood blockbusters and on CNN. To find out what Eric can say visit www.ivona.com. Just select his voice and then enter any text in the appropriate box for Eric to read it out. The service allows you to send your friends interesting pieces of information read out by Eric or to post them on a blog. 

[click heading for more]

W3C examines the next generation of speech technology

[nik's note:]

The W3C on Tuesday said the next generation of VoiceXML will include specifications for speaker verification.

"Speaker verification and identification is not only the best biometric for securing telephone transactions and communications, it can work seamlessly with speech recognition and speech synthesis in VoiceXML deployments," Ken Rehor, newly elected chairman of the VoiceXML Forum, said in a statement.
The W3C has now completed its desired requirements for VoiceXML 3.0 and expects to have a working draft of the specifications by the end of the first quarter, said James Larson, co-chair of the W3C Voice Browser Working Group.
In addition to the speaker identification requirements for VoiceXML 3.0, the W3C addressed the issue of extending its Speech Synthesis Markup Language (SSML) functionality to certain languages including Mandarin, Japanese and Korean.

[click heading for more]

Yahoo OneSearch 2.0 slowly spreads voice search

On Thursday, Yahoo slipped voice recognition into the OneSearch 2.0 home-screen shortcut--available for a smattering of Nokia Series 60 phones--and in the Yahoo! Go 3.0 files for select BlackBerry, Nokia Series 40, and Nokia Series 60 models, such as the BlackBerry Curve and high-end Nokia and Sony Ericsson phones. Those using older versions of either of these apps will have to download them anew to get the chatty update.

Operating the voice search is simple--on BlackBerry, just hold down on the green 'talk' button and speak your search term. OneSearch will start scouring Yahoo's database for answers as soon as you let go. Nokia owners can hit the pencil key to get going. Those without pencil keys will launch tier search by pressing the right shortcut key (labeled Y! OneSearch) and speaking or typing into the search box that appears. [click heading for more]

Nokia Picks Nuance For Speech Recognition And More; Will Open Up Technologies To Developers

Nokia is signing a multi-year deal worth "tens of millions of dollars" with Nuance Communications in an unusual arrangement, where Nokia will not only license Nuance's speech-recognition and predictive text technologies to use internally, but also to make them available to developers working with Nokia. Michael Thompson, GM for Nuance's mobile business unit, said in an interview that the deal is being called "the Open Interface Framework," however declined to give many specifics about the program, including when it would launch and whether developers would have to pay a fee to participate. [click heading for more]

top-VOX UK Launches Intelligent Pick by Voice Solution in the UK

The UK launch of the high performance solution for speech controlled picking and data capture heralds the start of the Thames Valley company, top-VOX UK, based in Camberley, Surrey.

The demands on such high-performance products are unrelenting. Logistics centres today are all about action. The forklift’s motor, lifting trucks being driven around and upset crates all combine to cause considerable background noise. Clearly, some Pick by Voice solutions are not able to cope under such conditions. It is a different story with the speaker-independent topSpeech-Lydia® system from leading European system provider topsystem. The system is being offered exclusively by top-VOX UK in the UK and the Commonwealth. Apart from sales, the company is also offering implementation, project management and maintenance of the software and hardware. The development of the noise resistant headset topSPEECH “NoiseMaster” signals the start for the company of a noticeable performance boost for Pick by Voice technology. The “NoiseMaster” reliably eliminates noise whatever the source. Totally in accord with problem-free order picking. Pick by Voice applications must also function reliably in tough and loud warehouse environments. Spoken commands and confirmations can be affected in this way by ambient noise and even be partly distorted. Regular and constant statistic noises can be filtered out easily with sophisticated software tools.Nevertheless, it is the strong dynamic noises such as the crash of a falling pallet that often interfere with optimal speech recognition. [click heading for more]

T-Mobile Signs Up for Nuance Speech Support

T-Mobile USA is using Nuance Communication’s Mobile Care software, the speech recognition company said today.
The software, originally developed by BeVocal and acquired by Nuance in April 2007, helps end users fix problems and perform account management through a speech interface. [click heading for more]

VoxWeb and Loquendo Bring Speech Technologies to Spain

In a bid to bring speech technologies to even more people and places in Spain, Loquendo and VoxWeb Soluciones de Voz have announced they worked together to create speech solutions for local councils in the area.

VoxWeb Soluciones de Voz, a Spanish speech solutions company made use of Loquendo Speech Recognition and Text to Speech solutions to develop speech applications particularly to complement Web portal services. [click heading for more]

'Say Where' Enables Speech-Recognition Queries on iPhone

Say Where, the first speech-recognition application for iPhone, launched Monday. My thoughts after some testing can be summed up as concisely as, "Thank God it's here," "It's pretty cool" and "It's free, so you should definitely try it."
A common complaint about iPhone has been the handset's lack of speech-recognition capabilities. Despite iPhone's versatility, the phone can't recognize voice commands to dial a contact, for example. To be clear, Say Where doesn't enable iPhone to translate speech into text messaging or dialing a contact, but it's a step in that direction: The app recognizes voice commands for Google Maps, Yelp, Traffic or Yellow Page queries. [click heading for more]